18 accepted papers
Diffusion models have gained prominence as powerful generative tools for solving inverse problems due to their ability to model complex data distributions. However, existing methods typically rely on complete knowledge of the forward observation process to compute gradients for guided sampling, limi
Generative models have emerged as a powerful paradigm in sequential recommendation due to their superior distribution modeling. However, long-tail data distributions inevitably induce popularity bias, as iterative generation trajectories gravitate toward dense clusters of popular items. Current debi
The reasoning large language model (RLLM) has been proven competitive in solving complex reasoning tasks such as mathematics, coding, compared to traditional LLM. However, the serving performance and behavior of RLLM remains \textit{unexplored}, which may undermine the deployment and utilization of…
While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on \textbf{sparse retrieval} tasks, potentially masking the degradation of High-Density Reasoning where Chain-of-Thought (CoT) coherence is critical. We introduce KVFundaBenc…
Web agents hold great potential for automating complex computer tasks, yet their interactions involve long horizons, multi-step decisions, and actions that can be irreversible. In such settings, outcome-based supervision is sparse and delayed, often rewarding incorrect trajectories and failing to su…
Admittance control is an important method for providing collaborative robots with precise manipulation and flexible contact behavior in industrial settings that often involve physical interaction. However, too rigid or high-frequency interactions by non-specialists will jeopardise the stability of t
Low-light image enhancement aims to improve visual quality under challenging lighting conditions while preserving details and color fidelity. Existing traditional algorithms and deep learning approaches, often struggle with balancing brightness enhancement and detail preservation, leading to issues…
Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Although existing compression methods reduce memory by evaluating the importance of individual tokens, they overlook critical s…
Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have demonstrated significant potential in automated fact-checking. However, existing methods face limitations in insufficient evidence utilization and lack of explicit verification criteria. Specifically, these approaches aggrega
Diffusion models, recognized for their effectiveness as generative priors, have become essential tools for addressing a wide range of visual challenges. Recently, there has been a surge of interest in leveraging Denoising processes for Regularization (DR) to solve inverse problems. However, existing…
This paper addresses the challenge of animal re-identification, an emerging field that shares similarities with person re-identification but presents unique complexities due to the diverse species, environments and poses. To facilitate research in this domain, we introduce OpenAnimals, a flexible an…
The reconstruction of physical fields from sparse measurements is pivotal in both scientific research and engineering applications. Traditional methods are increasingly supplemented by deep learning models due to their efficacy in extracting features from data. However, except for the low accuracy o…
The model extraction attack is an attack pattern aimed at stealing well-trained machine learning models' functionality or privacy information. With the gradual popularization of AI-related technologies in daily life, various well-trained models are being deployed. As a result, these models are consi…
Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelling across these criteria. Some recent works disclose the pitfalls of these ed…
Recently, significant progress has been made in generating high-quality sentence representations through contrastive learning. SimCSE-like models improve the uniformity of the representation space by pulling in positive examples and pushing out negative examples. However, these models often suffer f…
We study Comparative Preference Classification (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which entity is preferred over the other. High-quality CPC models can significantly benefit applications such as comparative quest…
Compliments and concerns in reviews are valuable for understanding users’ shopping interests and their opinions with respect to specific aspects of certain items. Existing review-based recommenders favor large and complex language encoders that can only learn latent and uninterpretable text represen…
This letter presents a force observer that estimates the external interaction forces from the measured joint position and joint actuation for a class of robotic manipulators. This is done without an explicit (physical) force or torque sensor, through an extended state observer (ESO) assuming a known